This example trains a multi-layer RNN (Elman, GRU, or LSTM) on a language modeling task. By default, the training script uses the PTB dataset, provided. The trained model can then be used by the generate script to generate new text.
python main.py --cuda # Train an LSTM on ptb with cuda (cuDNN). Should reach perplexity of 113
python generate.py # Generate samples from the trained LSTM model.The model uses the nn.RNN module (and its sister modules nn.GRU and nn.LSTM)
which will automatically use the cuDNN backend if run on CUDA with cuDNN installed.
The main.py script accepts the following arguments:
optional arguments:
-h, --help show this help message and exit
--data DATA location of the data corpus
--model MODEL type of recurrent net (RNN_TANH, RNN_RELU, LSTM, GRU)
--emsize EMSIZE size of word embeddings
--nhid NHID humber of hidden units per layer
--nlayers NLAYERS number of layers
--lr LR initial learning rate
--clip CLIP gradient clipping
--epochs EPOCHS upper epoch limit
--batch-size N batch size
--bptt BPTT sequence length
--seed SEED random seed
--cuda use CUDA
--log-interval N report interval
--save SAVE path to save the final model